BibTex RIS Cite

Assessing the desertification trend using neural network classification and object-oriented techniques (Case study: Changouleh watershed - Ilam Province of Iran)

Year 2016, Volume: 66 Issue: 2, 683 - 690, 01.07.2016
https://doi.org/10.17099/jffiu.75819

Abstract

Assessing the desertification trend using neural network classification and object-oriented techniques (Case study: Changouleh watershed - Ilam Province of Iran)

Abstract: Desertification consists of decline in production and ecological activities, which may happen due to either natural or unnatural (human) factors.This phenomenon is more evident in arid and semi-arid areas. The aim of this study is to assess the desertification trend using neural network classification and object-oriented techniques in Changouleh watershed which covers an area of 9949 hectare and is located in the south of Ilam province. For this study, TM and ETM+ satellite images of 1984 and 2013 were used. After conducting geometric and atmospheric corrections, images were classified using two neural network and object-orientedalgorithms. Moreover, to evaluate the accuracy and control the correctness of the obtained maps, typical parameters such as Kappa coefficient, the Confusion matrix, and stability of the classification were extracted for assessing the accuracy. The results show that most changes are related to increase in bare lands and decrease in poor and fair rangelands; therefore, approximately 18% of these areas has turned into desert. The results of evaluation of maps correctness show that these two methods are of high accuracy, but the object-oriented approach with Kappa coefficient (94%) and overall accuracy (96.26 %); in addition to being able to detect and categorize more classes, has a high accuracy compared to neural network method.

Keywords: Neural network classification, object-oriented classification, land use changes, Changouleh watershed

Sinir ağı sınıflandırma ve obje tabanlı sınıflandırma teknikleri kullanarak çölleşme eğilim değerlendirilmesi

Özet: Çölleşme nedeniyle üretim ve ekolojik faaliyetlerde düşüş oluşur. Bu düşüş doğal ya da doğal olmayan (insan) faktörlere bağlı olarak ortaya çıkmaktadır. Bu durum kurak ve yarı kurak bölgelerde daha belirgindir. Bu çalışmanın amacı, 9949 hektarlık alan kaplayan ve İlam eyaletinin güneyinde yer alan Changouleh havzasında sinir ağı sınıflandırma ve nesne yönelimli teknikleri kullanarak çölleşme eğilim değerlendirmesini ortaya koymaktır.   Bu çalışmada, 1984 ve 2013 yılı TM ve ETM + uydu görüntüleri kullanılmıştır. Geometrik ve atmosferik düzeltmeler yapıldıktan sonra, görüntüler iki sinir ağı ve nesne yönelimli algoritmalar kullanılarak sınıflandırılmıştır. Ayrıca, elde edilen haritaların doğruluğunu değerlendirmek ve kontrol etmek için, Kappa katsayısı, Karışıklık matris ve sınıflandırma istikrarı gibi tipik parametreler hariç tutulmuştur. Sonuçlar değişikliklerin çoğunun çıplak topraklardaki artış ve fakir mera alanlarındaki azalma ile ilişkili olduğunu göstermiştir; Bu nedenle, bu alanların yaklaşık% 18'i çöle dönüşmüştür. Harita doğruluk değerlendirme sonuçlarına göre, her iki yöntem (Kappa katsayısı (% 94))  ve (genel doğruluk (96,26%)) de yüksek doğruluk göstermektedir. Bunun yanı sıra nesne yönelimli yaklaşım ile; daha fazla sınıf kategorize etmek mümkündür ve sinir ağı yöntemine göre yüksek bir doğruluğa sahiptir.

Anahtar Kelimeler: Sinir ağı sınıflandırma, obje tabanlı sınıflandırma, arazi kullanım değişiklikleri, Changouleh havzası.

Received (Geliş): 20.07.2015 - Revised (Düzeltme): 26.10.2015 -   Accepted (Kabul): 27.10.2015

Cite (Atıf): Mohamadi, A., Heidarizadi, Z., Nourollahi, H., 2016. Assessing the desertification trend using neural network classification and object-oriented techniques (Case study: Changouleh watershed - Ilam Province of Iran). Journal of the Faculty of Forestry Istanbul University 66(2): 683-690. DOI: 10.17099/jffiu.75819

References

  • AlaviPanah, S.K., 2003. Applications of Remote Sensing in Geosciences (Soil Science), Tehran University Publications, Page 478.
  • Mohamadi, A. et al., 2009, Comparison of pixel based, object based, and decision tree classification methods in creating forest type maps using remote sensing data (Case Study: Astara Forest). Journal of Applied Research and Geographical Sciences 10(13): 7-26
  • Anderson, J., Hady, E., Roach, H., Wetter, T., 1976. A Land Cover Classification System For With remote Sensor Data. United States Government Printing Office, Washington.
  • Baatz, M., Schape, A., 1999. Object-oriented and Multi Scale Image Analysis in Semantic Networks, Proceeding of The 2nd International Symposium on Remote Sensing, 16-22 August, Ensched, ITC.
  • Babaev, G.A., 1999. Desert Problems andDesertification in Central ASIA. The researches of the Desert institute Springer - Verlag berlin, Heidelberg New York.
  • Bonyad, I., Haji Ghaderi, T., 2007. Mapping the Natural Forests of Zanjan Province Using Landsat 7 +ETM Sensor Data. Journal of Science and Technology of Agriculture and Natural Resources 42(11): 627-638.
  • Brothers, G.L., Fish, E.B., 1978. Image enhancement for vegetation pattern change analysis. Photogrammetric Engineering and Remote Sensing 44: 607-616
  • Chavez, P.S., 1996. Image-based atmospheric corrections-Revisited and improved. Photogrammetric Engineering and Remote Sensing, 62: 1025- 1036.
  • Coppin, P., Jonckheere, I., Nackaerts, K., Muys, B., Lambin, E., 2004. Digital change detection methods in ecosystem monitoring: A review. International Journal of Remote Sensing 10: 1565-1596.
  • Definiens Imaging GmbH, 2006. Definiens Professional5 User Guide, http://www.definiens.com/.Userguide.pdf, 249 pp.
  • Franklin, S. E., 2001. Remote Sensing for Sustainable Forest Management, CRC Press(Lewis), Boca Raton, FL, 407p.
  • Lu, D., Mausel, P., Brondi´zio, E. and Moran, E., 2004. Change detection techniques. INT. J. REMOTE SENSING, 20 JUNE, 2004, VOL. 25, NO. 12, 2365–2407.
  • Mashkou, M., (Translator), 1998. A Temporary Approach for Evaluating and Desertification Mapping. Food and Agriculture Organization of the United Nations (FAO), United Nations Environment Program (UNEP), Forests and Rangelands Research Institute.
  • Rezayi Moghadam, M et al., 2008. Classification of vegetation cover and land-use based on object-oriented technique and satellite images in West Azerbaijan Province, Watershed Management Researches Journal 87: 15-23.
  • Sen, A.K., Sharma, K.D., 1995. CausativeAgents Indicators of Monitoring and Desertificationin ASIA and the pacific region Scientific Publishers Jodhpur (INDIA), 41-58.
  • Terrill, W.R.,1994. AFAQ on vegetation in Remote Sensing, California Institute of Technology .
  • Vapnik, V., 1995. The Nature of Statistical Learning Theory. Springer-Verlag.
  • Zehtabian, Q.R., Tabatabaei, M.R., 2008. Investigation the desertification trend using satellite imagery processing and Geographical Information System. Journal of Desert 4(2).

Sinir ağı sınıflandırma ve obje tabanlı sınıflandırma teknikleri kullanarak çölleşme eğilim değerlendirilmesi

Year 2016, Volume: 66 Issue: 2, 683 - 690, 01.07.2016
https://doi.org/10.17099/jffiu.75819

Abstract

Çölleşme nedeniyle üretim ve ekolojik faaliyetlerde düşüş oluşur. Bu düşüş doğal ya da doğal olmayan (insan) faktörlere bağlı olarak ortaya çıkmaktadır. Bu durum kurak ve yarı kurak bölgelerde daha belirgindir. Bu çalışmanın amacı, 9949 hektarlık alan kaplayan ve İlam eyaletinin güneyinde yer alan Changouleh havzasında sinir ağı sınıflandırma ve nesne yönelimli teknikleri kullanarak çölleşme eğilim değerlendirmesini ortaya koymaktır. Bu çalışmada, 1984 ve 2013 yılı TM ve ETM + uydu görüntüleri kullanılmıştır. Geometrik ve atmosferik düzeltmeler yapıldıktan sonra, görüntüler iki sinir ağı ve nesne yönelimli algoritmalar kullanılarak sınıflandırılmıştır. Ayrıca, elde edilen haritaların doğruluğunu değerlendirmek ve kontrol etmek için, Kappa katsayısı, Karışıklık matris ve sınıflandırma istikrarı gibi tipik parametreler hariç tutulmuştur. Sonuçlar değişikliklerin çoğunun çıplak topraklardaki artış ve fakir mera alanlarındaki azalma ile ilişkili olduğunu göstermiştir; Bu nedenle, bu alanların yaklaşık% 18'i çöle dönüşmüştür. Harita doğruluk değerlendirme sonuçlarına göre, her iki yöntem (Kappa katsayısı (% 94)) ve (genel doğruluk (96,26%)) de yüksek doğruluk göstermektedir. Bunun yanı sıra nesne yönelimli yaklaşım ile; daha fazla sınıf kategorize etmek mümkündür ve sinir ağı yöntemine göre yüksek bir doğruluğa sahiptir

References

  • AlaviPanah, S.K., 2003. Applications of Remote Sensing in Geosciences (Soil Science), Tehran University Publications, Page 478.
  • Mohamadi, A. et al., 2009, Comparison of pixel based, object based, and decision tree classification methods in creating forest type maps using remote sensing data (Case Study: Astara Forest). Journal of Applied Research and Geographical Sciences 10(13): 7-26
  • Anderson, J., Hady, E., Roach, H., Wetter, T., 1976. A Land Cover Classification System For With remote Sensor Data. United States Government Printing Office, Washington.
  • Baatz, M., Schape, A., 1999. Object-oriented and Multi Scale Image Analysis in Semantic Networks, Proceeding of The 2nd International Symposium on Remote Sensing, 16-22 August, Ensched, ITC.
  • Babaev, G.A., 1999. Desert Problems andDesertification in Central ASIA. The researches of the Desert institute Springer - Verlag berlin, Heidelberg New York.
  • Bonyad, I., Haji Ghaderi, T., 2007. Mapping the Natural Forests of Zanjan Province Using Landsat 7 +ETM Sensor Data. Journal of Science and Technology of Agriculture and Natural Resources 42(11): 627-638.
  • Brothers, G.L., Fish, E.B., 1978. Image enhancement for vegetation pattern change analysis. Photogrammetric Engineering and Remote Sensing 44: 607-616
  • Chavez, P.S., 1996. Image-based atmospheric corrections-Revisited and improved. Photogrammetric Engineering and Remote Sensing, 62: 1025- 1036.
  • Coppin, P., Jonckheere, I., Nackaerts, K., Muys, B., Lambin, E., 2004. Digital change detection methods in ecosystem monitoring: A review. International Journal of Remote Sensing 10: 1565-1596.
  • Definiens Imaging GmbH, 2006. Definiens Professional5 User Guide, http://www.definiens.com/.Userguide.pdf, 249 pp.
  • Franklin, S. E., 2001. Remote Sensing for Sustainable Forest Management, CRC Press(Lewis), Boca Raton, FL, 407p.
  • Lu, D., Mausel, P., Brondi´zio, E. and Moran, E., 2004. Change detection techniques. INT. J. REMOTE SENSING, 20 JUNE, 2004, VOL. 25, NO. 12, 2365–2407.
  • Mashkou, M., (Translator), 1998. A Temporary Approach for Evaluating and Desertification Mapping. Food and Agriculture Organization of the United Nations (FAO), United Nations Environment Program (UNEP), Forests and Rangelands Research Institute.
  • Rezayi Moghadam, M et al., 2008. Classification of vegetation cover and land-use based on object-oriented technique and satellite images in West Azerbaijan Province, Watershed Management Researches Journal 87: 15-23.
  • Sen, A.K., Sharma, K.D., 1995. CausativeAgents Indicators of Monitoring and Desertificationin ASIA and the pacific region Scientific Publishers Jodhpur (INDIA), 41-58.
  • Terrill, W.R.,1994. AFAQ on vegetation in Remote Sensing, California Institute of Technology .
  • Vapnik, V., 1995. The Nature of Statistical Learning Theory. Springer-Verlag.
  • Zehtabian, Q.R., Tabatabaei, M.R., 2008. Investigation the desertification trend using satellite imagery processing and Geographical Information System. Journal of Desert 4(2).
There are 18 citations in total.

Details

Primary Language English
Journal Section Short Note (Kısa Not)
Authors

Abdolreza Mohamadi This is me

Zahedeh Heidarizadi

Hadi Nourollahi This is me

Publication Date July 1, 2016
Published in Issue Year 2016 Volume: 66 Issue: 2

Cite

APA Mohamadi, A., Heidarizadi, Z., & Nourollahi, H. (2016). Assessing the desertification trend using neural network classification and object-oriented techniques (Case study: Changouleh watershed - Ilam Province of Iran). Journal of the Faculty of Forestry Istanbul University, 66(2), 683-690. https://doi.org/10.17099/jffiu.75819
AMA Mohamadi A, Heidarizadi Z, Nourollahi H. Assessing the desertification trend using neural network classification and object-oriented techniques (Case study: Changouleh watershed - Ilam Province of Iran). J FAC FOR ISTANBUL U. July 2016;66(2):683-690. doi:10.17099/jffiu.75819
Chicago Mohamadi, Abdolreza, Zahedeh Heidarizadi, and Hadi Nourollahi. “Assessing the Desertification Trend Using Neural Network Classification and Object-Oriented Techniques (Case Study: Changouleh Watershed - Ilam Province of Iran)”. Journal of the Faculty of Forestry Istanbul University 66, no. 2 (July 2016): 683-90. https://doi.org/10.17099/jffiu.75819.
EndNote Mohamadi A, Heidarizadi Z, Nourollahi H (July 1, 2016) Assessing the desertification trend using neural network classification and object-oriented techniques (Case study: Changouleh watershed - Ilam Province of Iran). Journal of the Faculty of Forestry Istanbul University 66 2 683–690.
IEEE A. Mohamadi, Z. Heidarizadi, and H. Nourollahi, “Assessing the desertification trend using neural network classification and object-oriented techniques (Case study: Changouleh watershed - Ilam Province of Iran)”, J FAC FOR ISTANBUL U, vol. 66, no. 2, pp. 683–690, 2016, doi: 10.17099/jffiu.75819.
ISNAD Mohamadi, Abdolreza et al. “Assessing the Desertification Trend Using Neural Network Classification and Object-Oriented Techniques (Case Study: Changouleh Watershed - Ilam Province of Iran)”. Journal of the Faculty of Forestry Istanbul University 66/2 (July 2016), 683-690. https://doi.org/10.17099/jffiu.75819.
JAMA Mohamadi A, Heidarizadi Z, Nourollahi H. Assessing the desertification trend using neural network classification and object-oriented techniques (Case study: Changouleh watershed - Ilam Province of Iran). J FAC FOR ISTANBUL U. 2016;66:683–690.
MLA Mohamadi, Abdolreza et al. “Assessing the Desertification Trend Using Neural Network Classification and Object-Oriented Techniques (Case Study: Changouleh Watershed - Ilam Province of Iran)”. Journal of the Faculty of Forestry Istanbul University, vol. 66, no. 2, 2016, pp. 683-90, doi:10.17099/jffiu.75819.
Vancouver Mohamadi A, Heidarizadi Z, Nourollahi H. Assessing the desertification trend using neural network classification and object-oriented techniques (Case study: Changouleh watershed - Ilam Province of Iran). J FAC FOR ISTANBUL U. 2016;66(2):683-90.